JP2006320424A - Action teaching apparatus and method - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide an action teaching apparatus and method which can effectively teach players standard actions in rehabilitation exercise or the like. <P>SOLUTION: The standard actions are presented to a user 10 by a robot 20 and actions of the user 10 corresponding to the standard actions are recognized from images taken by cameras 31 and 32. A difference is detected between the actions of the user 10 recognized and the standard actions presented by the robot 20 and an advice for correcting the difference is outputted in a voice from a speaker 40. This enables the user 10 to correct his each wrong action following the vocal advice, thereby achieving the effective learning of the standard actions as compared with the unilateral presentation of actions with a video or the like. <P>COPYRIGHT: (C)2007,JPO&INPIT

Description

  The present invention relates to a motion teaching apparatus and method for teaching an exemplary body motion to a user in, for example, exercise for rehabilitation, operation of an electronic device, sports, and the like.

  With the development of medical technology, the average life expectancy has increased while the number of children has been decreasing year by year, and so society is aging rapidly. For this reason, there is an urgent need to develop a mechanism and environment that supports the elderly.

  Non-Patent Document 1 describes a technique for estimating a user's gesture by capturing a user's video captured by a camera into a computer and performing image processing, and operating a game machine according to the estimated gesture. ing. This makes it possible to enjoy the game without feeling a burden even for an elderly person who is unable to operate the controller of the game machine as desired because the fingertip is inconvenient or unfamiliar with the operation of the electronic device. .

Non-Patent Document 2 describes a system in which a robot teaches a user to perform keyboard input operations. In this system, a user's voice input to a microphone is taken into a computer and voice recognition processing is performed to recognize the input voice as a word. Then, the small robot arranged on the side of the keyboard is controlled so that the position of the key corresponding to the recognized word is pointed. As a result, the user can easily learn how to operate the keyboard from the robot any number of times, so that even an elderly person unaccustomed to operating electronic devices can learn key operations at their own pace.
Imai and two others, “Gesture operation of home video game machines using stereo cameras”, “The 19th Rehabilitation Engineering Conference Proceedings”, August 25, 2004, p. 191-192 Yoshino and 1 other, "Learning support system for PC key input operation for the elderly", "The 19th Rehabilitation Engineering Conference Proceedings", August 25, 2004, p. 201-202

  By the way, the proportion of people suffering from chronic diseases generally tends to increase with age. In order to recover from these diseases and maintain and improve health, it is effective to perform appropriate exercise as rehabilitation. However, conventionally, such exercise as rehabilitation has been performed under the instruction of an instructor in a specialized facility, and there is a problem that it is difficult for an elderly person to personally perform at home.

  In addition to rehabilitation, for example, when training to improve skills in sports, if there is no instructor who teaches the correct form, it is necessary to study by watching videos instead of the instructor is there. However, in such personal training, only information is received unilaterally, and the person who performs the training has to grasp for himself whether the action actually performed is appropriate. Therefore, there is a problem that the learning effect is inferior to the case where training is performed in response to the instruction of the instructor.

  The present invention has been made in view of such circumstances, and an object of the present invention is to provide an operation teaching apparatus and method that can effectively teach an exemplary operation to a user in a rehabilitation exercise or the like. is there.

An operation teaching apparatus according to a first aspect of the present invention includes an operation presentation unit that presents an exemplary operation to a user, and an operation recognition that recognizes the operation of the user corresponding to the operation presented by the operation presentation unit. Information providing information relating to advice for correcting a difference detected by the detection unit, a detection unit for detecting a difference between the motion presented by the motion presentation unit and the motion recognized by the motion recognition unit Part.
Preferably, the operation presentation unit repeatedly presents the same operation according to the detection result of the detection unit.

  The motion teaching apparatus may include a vital sign measurement unit that measures the vital sign of the user. In this case, the motion presentation unit may select and present a motion according to the measurement result of the vital sign measurement unit from a plurality of motions that can be presented. The information providing unit may select and provide information according to the measurement result of the vital sign measurement unit from among a plurality of pieces of information related to advice for correcting the difference detected by the detection unit.

  The motion teaching device may include an evaluation unit that evaluates the physical ability of the user according to a detection result of the detection unit. In this case, the operation presentation unit may select and present an operation according to the evaluation result of the evaluation unit from a plurality of operations that can be presented. The information providing unit may select and provide information according to the evaluation result of the evaluation unit among a plurality of pieces of information related to advice for correcting the difference detected by the detection unit.

  The motion teaching apparatus may include a voice recognition unit that recognizes the user's voice. In this case, the action presentation unit starts the action presentation, ends the action presentation, and a plurality of actions that can be presented according to the user's voice recognized by the voice recognition unit. You may perform at least 1 of the selection of the operation | movement shown to the said user.

  Further, the motion presentation unit is at least one of a robot demonstrating an exemplary motion, a video display unit that displays a video of the exemplary motion, and an audio output unit that outputs a voice teaching the exemplary motion. May be included.

  The motion teaching method according to the second aspect of the present invention includes a first step in which at least one of a robot, a video display unit, and an audio output unit presents an exemplary motion to a user, and the first step The user's motion corresponding to the motion presented in the process is photographed by the photographing unit from at least two positions, and based on the user's motion photographed by the photographing unit, the user's predetermined body part Based on the second step of acquiring the three-dimensional position information and the three-dimensional position information acquired in the second step, the operation presented in the first step and the user's operation photographed by the photographing unit And a fourth step of providing information related to advice for correcting the difference detected in the third step.

  According to the present invention, a difference between the presented action and the actual action performed by the user is detected, and advice for correcting this difference is provided to the user. Compared to the case where the action is presented, the exemplary action can be effectively taught to the user.

<First Embodiment>
FIG. 1 is a diagram showing an example of the configuration of the motion teaching apparatus according to the first embodiment of the present invention.
The motion teaching apparatus shown in FIG. 1 includes a robot 20, cameras 31 and 32, a speaker 40, and a control unit 100.
In addition, the control unit 100 includes a robot control unit 101, an action recognition processing unit 102, a detection unit 103, and an audio output unit 104.

The correspondence relationship between each component of the motion teaching apparatus shown in FIG. 1 and each component of the present invention is as follows.
A unit including the robot 20 and the robot control unit 101 is an embodiment of the motion presentation unit of the present invention.
A unit including the cameras 31 and 32 and the motion recognition processing unit 102 is an embodiment of the motion recognition unit of the present invention.
The unit including the speaker 40 and the audio output unit 104 is an embodiment of the information providing unit of the present invention.

  The robot 20 is a device for presenting an exemplary motion (exemplary motion) to the user 10, and the robot controller 101 controls each part (hand, foot, neck, etc.) formed in the shape of a human body. Move according to.

  The cameras 31 and 32 capture images of the user 10 from different positions and output the image signals to the control unit 100.

  The speaker 40 outputs a sound corresponding to the sound signal output from the sound output unit 104.

  The control unit 100 performs various processes and controls related to the overall operation of the motion teaching apparatus. That is, the control unit 100 controls the robot 20 to demonstrate an exemplary operation, and images the operation of the user 10 performed in accordance with the demonstration with the cameras 31 and 32. Then, three-dimensional position information of a predetermined body part of the user 10 is acquired based on the photographed movement, and advice for correcting the difference between the position information and the model movement demonstrated by the robot 20 is used as a voice. Output from the speaker 40.

FIG. 2 is a diagram illustrating an example of the configuration of the control unit 100.
For example, as shown in FIG. 2, the control unit 100 includes an input unit 110, a display unit 111, an interface unit 112, a storage device 113, a RAM 114, a ROM 115, and a computer 116.

  The input unit 110 is a device for inputting information corresponding to a user operation, such as a keyboard and a mouse.

  The display unit 111 includes a display device such as a liquid crystal display or a CRT display, and displays an image based on a video signal supplied from the computer 116.

  The interface unit 112 exchanges signals between the input / output device of the computer 116 and external devices such as the robot 20, the cameras 31 and 32, and the speaker 40. That is, a control signal is output to the robot 20, a video signal is captured from the cameras 31 and 32, and an audio signal is output to the speaker 40.

  The storage device 113 is a device capable of storing a relatively large amount of data, such as a hard disk device or a magneto-optical disk device, and stores an operating system and application programs of the computer 116 and various data. For example, the control data of the robot 20, advice voice data output from the speaker 40, and the like are stored.

The RAM 114 stores data that needs to be temporarily stored in the process of the computer 116, program code of the computer 116, and the like.
The ROM 115 stores constant data used in the computer 116, a startup program, and the like.

  The computer 116 executes various processes according to programs stored in the ROM 115 and the storage device 113. Processing of functional blocks (robot control unit 101, motion recognition processing unit 102, detection unit 103, voice output unit 104, etc.) described below is realized by computer 116.

  The robot control unit 101 controls the robot 20 based on the control data stored in the storage device 113 and demonstrates an exemplary operation.

The exemplary operation is constituted by a series of a plurality of operations, for example, and the storage device 113 stores control data for causing the robot 20 to demonstrate this series of operations (hereinafter referred to as operation patterns). Based on the control data stored in the storage device 113, the robot control unit 101 causes the robot 20 to perform each operation constituting the operation pattern in order.
However, when the detection unit 103 described later detects a certain difference or more between the motion of the user 10 recognized by the motion recognition processing unit 102 and the exemplary motion of the robot 20, the robot control unit 101 may The robot 20 is repeatedly demonstrated in motion.

  Further, when control data capable of demonstrating a plurality of operation patterns is stored in the storage device 113, the robot control unit 101 displays a menu screen for selecting an operation pattern on the display unit 111, for example. The user 10 is prompted to make a selection. When the user 10 selects an operation pattern by operating the input unit 110, the robot control unit 101 causes the robot 20 to demonstrate the selected operation pattern.

  The motion recognition processing unit 102 is a user photographed by the cameras 31 and 32 during a predetermined period in which the user 10 operates in accordance with the demonstration of the robot 20 (for example, a predetermined period during or after the demonstration of the robot 20). Processing for recognizing 10 operations is performed. That is, the three-dimensional position information of a predetermined body part of the user 10 is acquired based on the actions of the user 10 taken by the two cameras (31, 32) during this period.

  For example, the motion recognition processing unit 102 uses an RRF (radial reach filter) based on an image captured by one of the two cameras (31, 32) and a background image captured in advance without the user 10. The image of the user 10 is extracted from the captured image by an image processing technique such as).

Next, the motion recognition processing unit 102 identifies which part of the image captured by one camera corresponds to which part of the image captured by the other camera based on, for example, the luminance distribution of the pixels. . Based on the information on the position of the corresponding two parts on the screen, the installation positions of the cameras 31 and 32, the shooting direction, etc., the three-dimensional position of the actual subject that the two parts are projected in common is obtained. calculate.
Further, the motion recognition processing unit 102 estimates which part of the image corresponds to which body part (head, hand, foot, etc.) of the user 10 based on the shape and area of each image.
Through the above processing, the motion recognition processing unit 102 acquires information regarding the three-dimensional position of the predetermined body part of the user 10.

  The detection unit 103 detects a difference between the operation of the user 10 recognized by the operation recognition processing unit 102 and the exemplary operation demonstrated by the robot 20 by the robot control unit 101.

The detection unit 103 detects, for example, how far the position of the predetermined body part calculated by the motion recognition processing unit 102 is in which direction with respect to the position required in the exemplary motion presented to the user 10. .
In addition to the position difference, for example, the movement speed and acceleration of the predetermined body part calculated by the motion recognition processing unit 102, the number of times the body part moves over a predetermined distance per unit time, the cycle, etc. Various characteristic values representing the movement of the body part may be calculated, and it may be detected whether the characteristic value is larger or smaller than the value required in the exemplary movement or how far away.

The audio output unit 104 reads out advice audio data for correcting the difference detected by the detection unit 103 from the storage device 113, and outputs the audio from the speaker 40.
For example, when the detection unit 103 detects that the position of the right arm of the user 10 is lower than that of the exemplary action, the audio output unit 104 displays audio data with a content such as “Please extend the right arm a little higher”. The data is read from the storage device 113 and the sound is output from the speaker 40.

  Here, the operation of the motion teaching apparatus having the above-described configuration shown in FIG. 1 will be described with reference to the flowchart shown in FIG.

Step ST100:
The robot control unit 101 selects an operation pattern for performing a demonstration from a plurality of operation patterns in accordance with an instruction from the user 10 input to the input unit 110.

Step ST105 (first step):
The robot control unit 101 causes the robot 20 to demonstrate the first exemplary operation in the operation pattern selected in step ST100.

Step ST110 (second step):
The motion recognition processing unit 102 performs a predetermined body of the user 10 on the basis of images of the user 10 captured by the cameras 31 and 32 during a predetermined period in which the user 10 operates in accordance with the demonstration of the robot 20. The three-dimensional position information of the part is acquired.

Step ST115 (third process):
Based on the three-dimensional position information acquired by the motion recognition processing unit 102, the detection unit 103 detects a difference between the exemplary motion that the robot control unit 101 has demonstrated to the robot 20 and the motion of the user 10.

Steps ST120, ST125, ST130:
If the detection unit 103 detects a certain difference or more between the exemplary operation of the robot 20 and the operation of the user 10, the robot control unit 101 returns to step ST105 and again performs the same exemplary operation on the robot 20. Let me demonstrate. And when performing this demonstration, the audio | voice output part 104 reads the audio | voice data for advice according to the detection result of the detection part 103 from the memory | storage device 113, and outputs it from the speaker 40 (step ST125, 4th process).
On the other hand, when the difference detected by the detection unit 103 is not equal to or greater than a certain level, the robot control unit 101 selects the next operation in the current operation pattern (ST130), and this exemplary operation is performed by the process after step ST105. To demonstrate.

As described above, according to the motion teaching apparatus shown in FIG. 1, an exemplary motion is presented to the user 10 by the robot 20, and the motion of the user 10 corresponding to this exemplary motion is displayed on the captured images of the cameras 31 and 32. Recognized on the basis. Then, a difference between the recognized action of the user 10 and the model action presented by the robot 20 is detected, and advice for correcting this difference is output from the speaker 40 as a sound.
Therefore, the user 10 can correct the action according to the voice advice when performing the wrong action, and learns the model action more effectively than when the action is presented unilaterally in a video or the like. can do.

  In addition, by learning exemplary correct actions according to the present embodiment, the effect of exercise can be obtained to the maximum. For example, when the present embodiment is applied to rehabilitation exercise, a significant effect can be obtained in restoring the physical function of the user and maintaining / promoting health. When this embodiment is applied to sports training, it can greatly contribute to improvement of user skills.

When performing rehabilitation and training under the guidance of a specialized instructor, it is difficult to learn movements according to their own pace due to time constraints. In particular, elderly people whose learning pace is slowed down due to low physical fitness, etc. need to learn over time, so instruction by an instructor who can occupy only a limited amount of time is physically or psychologically for the elderly May be a burden.
According to the motion teaching apparatus according to the present embodiment, it is possible to easily learn motion at your own pace without being restricted by time or place, so an environment suitable for rehabilitation of the elderly and disabled Can be provided.

In addition, the conventional method in which information is unilaterally given tends to be monotonous and quickly gets bored. On the other hand, according to the motion teaching apparatus according to the present embodiment, since advice is provided according to the user's motion, the learning is more interesting and the user's motivation can be enhanced.
Moreover, since it is possible to easily learn at home, it is possible to increase the repetition and continuity of learning compared to the case where rehabilitation and training are conducted through a facility.

  Furthermore, since the motion is presented by the three-dimensional movement of the robot 20, the user can easily understand the motion. Thereby, a user can be made to wear a correct operation.

<Second Embodiment>
Next, a second embodiment of the present invention will be described.
In the motion teaching apparatus according to the second embodiment, the content of the motion to be presented and the content of the advice are changed according to the vital sign of the user.

FIG. 4 is a diagram showing an example of the configuration of the motion teaching apparatus according to the second embodiment of the present invention.
The motion teaching apparatus shown in FIG. 4 includes a robot 20, cameras 31, 32, a speaker 40, a vital sign measuring instrument 50, and a control unit 100A. The control unit 100A includes a robot control unit 101A, an action recognition processing unit 102, a detection unit 103, an audio output unit 104A, and a measurement processing unit 105.
Since the same reference numerals in FIG. 1 and FIG. 4 indicate the same constituent elements, only the constituent elements different from the motion teaching apparatus shown in FIG. 1 will be described below.

  The vital sign measuring device 50 measures signs related to the life activity of the user 10 such as heart rate, blood pressure, oxygen saturation, respiratory rate, body temperature, sweating, and electroencephalogram.

  The measurement processing unit 105 takes in the measurement result of the vital sign measuring instrument 50 and passes it to the robot control unit 101A and the voice output unit 104A. The measurement processing unit 105 may average the measurement results of the vital sign measuring device 50 in terms of time.

  The unit including the vital sign measuring device 50 and the measurement processing unit 105 is an embodiment of the vital sign measuring unit of the present invention.

The robot control unit 101A causes the robot 20 to demonstrate the operation selected according to the measurement result of the vital sign measuring device 50 from the plurality of operations that can be presented. For example, when it is estimated that the fatigue level of the user 10 is increased to a certain level or more based on the measurement result of the vital sign, an operation with a lower fatigue level is selected from the current operation pattern or another operation pattern. Let the robot 20 demonstrate.
Other operations are the same as those of the robot control unit 101.

104 A of audio | voice output parts output the audio | voice selected according to the measurement result of the vital sign measuring device 50 among the some audio | voices for advice for correct | amending the difference which the detection part 103 detected from the speaker 40. FIG. For example, when it is estimated that the fatigue level of the user 10 is increased to a certain level or more based on the measurement result of the vital sign, the voice of advice is selected so that the physical load becomes relatively small.
Other operations are the same as those of the audio output unit 104.

  Here, the operation of the motion teaching apparatus shown in FIG. 4 having the above-described configuration will be described with reference to the flowchart shown in FIG.

Step ST200:
The measurement processing unit 105 captures the measurement result of the vital sign measuring device 50.

Step ST205:
The robot control unit 101A selects an operation pattern to perform a demonstration from a plurality of operation patterns according to the instruction of the user 10 input to the input unit 110 or the measurement result of the vital sign measuring device 50 captured in step ST200. To do.

Step ST210 (first step):
The robot control unit 101A causes the robot 20 to demonstrate the first exemplary motion in the motion pattern selected in step ST205.

Step ST215 (second step):
The motion recognition processing unit 102 acquires the three-dimensional position information of a predetermined body part of the user 10 during a predetermined period in which the user 10 operates in accordance with the demonstration of the robot 20.

Step ST220 (third process):
Based on the three-dimensional position information acquired by the motion recognition processing unit 102, the detection unit 103 detects a difference between the exemplary motion that the robot control unit 101A demonstrated to the robot 20 and the motion of the user 10.

Step ST225:
The measurement processing unit 105 captures the measurement result of the vital sign measuring device 50.

Steps ST230, ST235, ST240:
When the detection unit 103 detects a certain difference or more between the exemplary operation of the robot 20 and the operation of the user 10, the robot control unit 101A returns to step ST210 and again performs the same exemplary operation on the robot 20. Let me demonstrate.
When performing this demonstration, the audio output unit 104A outputs the advice audio considering the measurement result of the vital sign measuring device 50 in addition to the detection result of the detection unit 103 from the speaker 40 (step ST235, fourth step). ).
For example, when it is estimated that the fatigue level of the user 10 is increased to a certain level or more based on the measurement result of vital signs, the voice of advice is selected so that the physical load is reduced.

On the other hand, when the difference detected by the detection unit 103 is not equal to or greater than a certain level, the robot control unit 101A selects the next operation in consideration of the measurement result of the vital sign measuring instrument 50 (ST240), and the selected exemplary operation Is demonstrated by the robot 20 in the process after step ST210.
For example, when it is estimated from the measurement result of the vital sign measuring device 50 that the physical condition of the user 10 is in the normal state, the robot control unit 101A selects the next operation in the current operation pattern as usual. On the other hand, when it is estimated from the measurement result of the vital sign measuring instrument 50 that the user 10 is more than a certain amount of fatigue, the robot control unit 101A includes a load that is included in the current operation pattern or another operation pattern. Choose a light operation.

  Note that the robot control unit 101A may determine whether to repeat the same operation according to the measurement result of the vital sign measurement device 50. For example, even when the difference detected by the detection unit 103 is greater than or equal to a certain level, if the user 10 is assumed to be fatigued by a certain amount or more according to the measurement result of the vital sign measuring instrument 50, the same operation is performed. The process may proceed to step ST240 while avoiding repetition.

  As described above, according to the motion teaching apparatus according to the present embodiment, it is possible to adaptively change the content of the motion to be practiced and the content of the advice according to the measurement result of the vital sign of the user 10. Therefore, even if the elderly are particularly ill, such as an elderly person, it is possible to perform an appropriate exercise while avoiding an unreasonable load.

<Third Embodiment>
Next, a third embodiment of the present invention will be described.
In the motion teaching apparatus according to the third embodiment, the motion to be presented and the content of advice are changed according to the physical ability of the user.

FIG. 6 is a diagram showing an example of the configuration of the motion teaching apparatus according to the third embodiment of the present invention.
The motion teaching apparatus shown in FIG. 6 includes a robot 20, cameras 31, 32, a speaker 40, and a control unit 100B. The control unit 100B includes a robot control unit 101B, an action recognition processing unit 102, a detection unit 103, an audio output unit 104B, and an evaluation unit 106.
Since the same reference numerals in FIG. 1 and FIG. 6 indicate the same components, only the components different from the motion teaching device shown in FIG. 1 will be described below.

The evaluation unit 106 evaluates the physical ability of the user 10 according to the detection result of the detection unit 103. For example, the difference in motion detected by the detection unit 103 is averaged by assigning a weight according to the degree of difficulty for each motion, and the physical ability of the user 10 is ranked according to the average value.
Alternatively, the number of repeated presentations of the same action by the robot control unit 101B may be counted, and the rank may be adjusted such that the smaller the number, the higher the evaluation of physical ability.

The robot control unit 101B causes the robot 20 to demonstrate the operation selected from the plurality of operations that can be presented according to the evaluation result of the evaluation unit 106. For example, when the evaluation of the evaluation unit 106 becomes high, an operation with a higher difficulty level is selected from the current operation pattern or another operation pattern, and the robot 20 is made to demonstrate.
Other operations are the same as those of the robot control unit 101.

The sound output unit 104B outputs, from the speaker 40, the sound selected according to the evaluation result of the evaluation unit 106 among the plurality of advice sounds for correcting the difference detected by the detection unit 103. For example, the voice of the advice is selected so that the difference detected by the detection unit 103 becomes smaller as the evaluation of the evaluation unit 106 becomes higher (that is, a more accurate operation is requested).
Other operations are the same as those of the audio output unit 104.

  Here, the operation of the motion teaching apparatus having the above-described configuration shown in FIG. 6 will be described with reference to the flowchart shown in FIG.

Step ST300:
The robot control unit 101B selects an operation pattern for performing a demonstration from a plurality of operation patterns in accordance with an instruction from the user 10 input to the input unit 110.

Step ST305 (first step):
The robot control unit 101B causes the robot 20 to demonstrate the first exemplary operation in the operation pattern selected in step ST300.

Step ST310 (second step):
The motion recognition processing unit 102 acquires the three-dimensional position information of a predetermined body part of the user 10 during a predetermined period in which the user 10 operates in accordance with the demonstration of the robot 20.

Step ST315 (third process):
Based on the three-dimensional position information acquired by the motion recognition processing unit 102, the detection unit 103 detects a difference between the exemplary motion that the robot control unit 101B demonstrated to the robot 20 and the motion of the user 10.

Step ST320:
The evaluation unit 106 evaluates the physical ability of the user 10 according to the detection result of the detection unit 103.

Steps ST325, ST330, ST335:
If the detection unit 103 detects a certain difference or more between the exemplary motion of the robot 20 and the motion of the user 10, the robot control unit 101B returns to step ST305 and again performs the same exemplary motion on the robot 20. Let me demonstrate.
When performing this demonstration, the audio output unit 104B outputs, from the speaker 40, advice audio that takes into consideration the evaluation result of the evaluation unit 106 in addition to the detection result of the detection unit 103 (step ST330, fourth step).
For example, the advice voice is selected so that the higher the evaluation of the evaluation unit 106 is, the more accurate operation is requested.

On the other hand, if the difference detected by the detection unit 103 is not equal to or greater than a certain level, the robot control unit 101B selects the next operation in consideration of the evaluation result of the evaluation unit 106 (ST335), and performs this exemplary operation after step ST305. In this process, the robot 20 is demonstrated.
For example, when the evaluation result of the evaluation unit 106 is not different from the evaluation during the previous operation, the robot control unit 101B selects the next operation in the current operation pattern as usual. On the other hand, when the evaluation result of the evaluation unit 106 is higher than that at the previous operation, the robot control unit 101B selects a more difficult operation included in the current operation pattern or another operation pattern. .

  The robot control unit 101B may determine whether to repeat the same operation according to the evaluation result of the evaluation unit 106. For example, even if the difference above a certain level is not detected in the detection unit 103, the same operation is repeated if the physical ability of the user 10 is estimated to be somewhat high from the evaluation result of the evaluation unit 106. A more exemplary operation may be requested from the user 10.

  As described above, according to the motion teaching device according to the present embodiment, it is possible to adaptively change the content of the motion to practice and the content of advice according to the evaluation result of the physical ability of the user 10. Thereby, since the suitable operation | movement according to the user's 10 physical ability can be selected, the effect (health improvement and skill improvement) of action learning can further be improved.

<Fourth Embodiment>
Next, a fourth embodiment of the present invention will be described.
In the motion teaching apparatus according to the fourth embodiment, the start and end of the motion presentation can be controlled by the user's voice.

FIG. 8 is a diagram showing an example of the configuration of the motion teaching apparatus according to the fourth embodiment of the present invention.
The motion teaching apparatus shown in FIG. 8 includes a robot 20, cameras 31, 32, a speaker 40, a microphone 60, and a control unit 100C. The control unit 100C includes a robot control unit 101C, an action recognition processing unit 102, a detection unit 103, a voice output unit 104, and a voice recognition processing unit 107.
Since the same reference numerals in FIG. 1 and FIG. 8 indicate the same components, only the components different from the motion teaching apparatus shown in FIG. 1 will be described below.

The microphone 60 inputs a voice uttered by the user 10 and converts it into a voice signal.
The voice recognition processing unit 107 performs processing for recognizing the voice of the user 10 as a character or a word based on the voice signal output from the microphone 60.

  The robot control unit 101C starts and ends the presentation of the operation by the robot 20 in accordance with the voice of the user 10 recognized by the voice recognition processing unit 107. Further, an operation pattern to be actually presented is selected from a plurality of operation patterns that can be presented to the user 10 according to the recognized voice.

For example, when the voice recognition processing unit 107 recognizes the voice of the user 10 “Start!”, The robot control unit 101C starts demonstration of the operation by the robot 20, and the user 10 “End!” In the middle of the demonstration. Is recognized, the demonstration of the robot 20 is finished.
In addition, when the three motion patterns given the names “1”, “2”, and “3” can be presented, the voice recognition processing unit 107 recognizes the voice of the user 10 “Start 1”! At this time, the robot control unit 101C selects the presentation of the motion pattern “1” and starts presenting the motion.
Other operations of the robot control unit 101C are the same as those of the robot control unit 101.

  Here, the operation of the motion teaching apparatus shown in FIG. 8 having the above-described configuration will be described with reference to the flowchart shown in FIG.

Step ST400:
The robot control unit 101 </ b> C suspends the demonstration start of the robot 20 until the voice recognition processing unit 107 recognizes the voice of the user 10 requesting the start of the operation.

Step ST405:
For example, when the voice recognition processing unit 107 recognizes the voice “Start 1!”, The robot control unit 101C selects an operation pattern given the name “1” according to the voice.

Step ST410 (first step):
The robot control unit 101C causes the robot 20 to demonstrate the first exemplary operation in the operation pattern selected in step ST405.

Step ST415 (second process):
The motion recognition processing unit 102 acquires the three-dimensional position information of a predetermined body part of the user 10 during a predetermined period in which the user 10 operates in accordance with the demonstration of the robot 20.

Step ST420 (third process):
Based on the three-dimensional position information acquired by the motion recognition processing unit 102, the detection unit 103 detects a difference between the exemplary motion that the robot control unit 101C demonstrated to the robot 20 and the motion of the user 10.

Step ST425:
When the voice recognition processing unit 107 recognizes the voice (for example, “End!”) Of the user 10 requesting the end of the operation during or after the demonstration of the robot 20, the robot control unit 101C ends the demonstration of the robot 20. If the voice recognition processing unit does not recognize such voice, the process proceeds to step ST430.

Steps ST430, ST435, ST440:
When the detection unit 103 detects a certain difference or more between the exemplary operation of the robot 20 and the operation of the user 10, the robot control unit 101C returns to step ST410 and again applies the same exemplary operation to the robot 20. Let me demonstrate. And when performing this demonstration, the audio | voice output part 104 reads the audio | voice data for advice according to the detection result of the detection part 103 from the memory | storage device 113, and outputs it from the speaker 40 (step ST435, 4th process).
On the other hand, if the difference detected by the detection unit 103 is not greater than or equal to a certain level, the robot control unit 101 selects the next operation in the current operation pattern (ST440), and this exemplary operation is processed after step ST410. Let robot 20 demonstrate.

  As described above, according to the motion teaching apparatus according to the present embodiment, the start and end of the demonstration of the exemplary motion by the robot 20 and the selection of the motion pattern can be easily performed by the user's voice. Thereby, the apparatus can be used very easily without memorizing troublesome operations. In addition, since it is possible for an elderly person or a physically handicapped person to easily learn rehabilitation exercises alone, the operating rate of the apparatus can be improved and the health of the user can be improved.

  As mentioned above, although several embodiment of this invention was described, this invention is not limited to said form, A various modification | change is possible.

For example, in the above-described embodiment, an example in which an exemplary motion is presented by a robot is given, but the present invention is not limited to this. For example, an exemplary operation may be presented as a two-dimensional or three-dimensional image by projecting a person, a living thing, an animation character, or the like on a display device by a video technique such as computer graphics.
In addition, when the subject is a blind person, the operation may be taught by voice.
Furthermore, you may show an operation | movement to a user combining these some presentation means.
As described above, according to the present invention, various devices can be applied to the operation presentation unit, so that the hardware configuration can be flexibly selected according to the needs of the user.

  In the above-described embodiment, the user's action is recognized by the video shot by the camera, but the present invention is not limited to this. For example, the user's motion may be recognized using a camera in combination with an acceleration sensor, a tilt sensor, an orientation sensor, an optical sensor, etc. worn by the user, or the user's motion may be recognized only with these sensors. good.

  In the embodiment described above, an example in which advice is provided to the user by voice is shown, but the present invention is not limited to this. For example, advice may be provided by video on a TV monitor or the like, or advice may be provided by light (such as blinking of a lamp), mechanical vibration, or electrical stimulation.

The same hardware may be used to present actions and provide advice.
For example, when the operation is presented and the advice is provided by video, both videos may be displayed on the same television monitor. When presenting an operation and providing advice by voice, both voices may be output from the same speaker.

  Each component of this embodiment can be connected by wireless communication as well as wired communication. For example, the vital sign measuring device may transmit the measurement result to the control unit by wireless communication. Thus, the user can concentrate on learning the operation without being disturbed by unnecessary wiring.

  Each component of the present invention can also be connected via a network such as the Internet. For example, in the example of FIG. 1, it is also possible to connect a computer device constituting the control unit 100 and devices such as the robot 20, the cameras 31 and 32, and the speaker 40 via a network. This makes it possible to use this apparatus even in places where computer equipment cannot be arranged.

It is a figure which shows an example of a structure of the operation | movement teaching apparatus which concerns on 1st Embodiment. It is a figure which shows an example of a structure of a control part. It is a flowchart for demonstrating operation | movement of the operation | movement teaching apparatus shown in FIG. It is a figure which shows an example of a structure of the operation | movement teaching apparatus which concerns on 2nd Embodiment. It is a flowchart for demonstrating operation | movement of the operation | movement teaching apparatus shown in FIG. It is a figure which shows an example of a structure of the operation | movement teaching apparatus which concerns on 3rd Embodiment. It is a flowchart for demonstrating operation | movement of the operation | movement teaching apparatus shown in FIG. It is a figure which shows an example of a structure of the operation | movement teaching apparatus which concerns on 3rd Embodiment. It is a flowchart for demonstrating operation | movement of the operation | movement teaching apparatus shown in FIG.

Explanation of symbols

DESCRIPTION OF SYMBOLS 10 ... User, 20 ... Robot, 31, 32 ... Camera, 40 ... Speaker, 50 ... Vital sign measuring device, 60 ... Microphone, 100, 100A, 100B, 100C ... Control part, 101, 101A, 101B, 101C ... Robot Control unit, 102 ... motion recognition processing unit, 103 ... detection unit, 104, 104A, 104B ... voice output unit, 105 ... measurement processing unit, 106 ... evaluation unit, 107 ... voice recognition processing unit

Claims (11)

An action presentation unit that presents exemplary actions to the user;
An action recognition unit for recognizing the action of the user corresponding to the action presented by the action presentation unit;
A detection unit for detecting a difference between the motion presented by the motion presentation unit and the motion recognized by the motion recognition unit;
An operation teaching device comprising: an information providing unit that provides information on advice for correcting the difference detected by the detection unit. The operation presentation unit repeatedly presents the same operation according to the detection result of the detection unit,
The motion teaching apparatus according to claim 1. It has a vital sign measurement unit that measures the vital signs of the user,
The operation presentation unit selects and presents an operation according to the measurement result of the vital sign measurement unit from a plurality of operations that can be presented.
The motion teaching apparatus according to claim 1 or 2. It has a vital sign measurement unit that measures the vital signs of the user,
The information providing unit selects and provides information according to the measurement result of the vital sign measurement unit among a plurality of pieces of information related to advice for correcting the difference detected by the detection unit.
The motion teaching apparatus according to claim 1 or 2. According to the detection result of the detection unit, the evaluation unit for evaluating the physical ability of the user,
The operation presentation unit selects and presents an operation according to the evaluation result of the evaluation unit from a plurality of operations that can be presented.
The motion teaching apparatus according to claim 1 or 2. According to the detection result of the detection unit, the evaluation unit for evaluating the physical ability of the user,
The information providing unit selects and provides information according to the evaluation result of the evaluation unit among a plurality of pieces of information related to advice for correcting the difference detected by the detection unit.
The motion teaching apparatus according to claim 1 or 2. A voice recognition unit that recognizes the user's voice;
The operation presentation unit is responsive to the user's voice recognized by the voice recognition unit,
The start of an action presentation,
The end of the presentation of the action, and
Selecting at least one of actions to be presented to the user from a plurality of actions that can be presented;
The motion teaching apparatus according to claim 1 or 2. The action presentation unit
A robot demonstrating exemplary movements,
An image display unit for displaying an image of an exemplary operation; and
Including at least one sound output unit that outputs sound teaching an exemplary operation;
The motion teaching device according to any one of claims 1 to 7. The motion recognition unit
A photographing unit for photographing the user from at least two positions;
A position information acquisition unit that acquires three-dimensional position information of a predetermined body part of the user based on an action of the user imaged by the imaging unit;
The motion teaching device according to any one of claims 1 to 7. The information providing unit provides information on the advice using at least one of video, sound, light, vibration, and electrical stimulation;
The motion teaching device according to any one of claims 1 to 7. A first step in which at least one of a robot, a video display unit, and an audio output unit presents an exemplary operation to the user;
The user's motion corresponding to the motion presented in the first step is photographed by the photographing unit from at least two positions, and the user's predetermined motion is determined based on the user's motion photographed by the photographing unit. A second step of acquiring three-dimensional position information of the body part of
A third step of detecting a difference between the motion presented in the first step and the motion of the user photographed by the photographing unit based on the three-dimensional position information acquired in the second step;
A fourth step of providing information relating to advice for correcting the difference detected in the third step.

Images